Speech recognition system, speech recognition apparatus, and speech recognition method

• US 7,174,299 B2
• Filed: 10/10/2001
• Issued: 02/06/2007
• Est. Priority Date: 08/18/1995
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Ikeda, Yuji, Fujii, Kenichi, Shimizu, Tomoyuki, Ito, Fumiaki, Ueda, Takaya
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/972,996
• Publication Number:
  US 20020046023A1
• Time in Patent Office: 1,945 Days
• Field of Search: 704/270, 704/251, 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

This invention has as its object to provide a speech recognition system to which a client and a device that provides a speech recognition process are connected, which provides a plurality of usable speech recognition means to the client, and which allows the client to explicitly switch and use the plurality of speech recognition means connected to the network. To achieve this object, a speech recognition system of this invention has speech input means for inputting speech at the client, designation means for designating one of the plurality of usable speech recognition means, and processing means for making the speech recognition means designated by the designation means recognize speech input from the speech input means.

Claims

1. A speech recognition apparatus comprising:

storage means for storing a keyword corresponding to an external speech recognition apparatus;

first receiving means for receiving speech information;

decision means for deciding whether or not the speech information received by said receiving means includes a keyword stored in said storing means;

second receiving means for, if said decision means decides that the speech information includes a keyword stored in said storage means, sending the speech information except for the keyword portion to an external speech recognition apparatus corresponding to the keyword, and receiving a speech recognition result from the external speech recognition apparatus; and

speech recognition means for, if said decision means decides that the speech information does not include a keyword stored in said storage means, recognizing the speech information.

2. A speech recognition method performed on a speech recognition apparatus which recognizes speech information, said method comprising:

a first receiving step of receiving speech information;

a decision step of deciding whether or not the speech information received in said receiving step includes a keyword corresponding to an external speech recognition apparatus;

a second receiving step of, if said decision step decides that the speech information includes a keyword corresponding to an external speech recognition apparatus, sending the speech information except for the keyword portion to the external speech recognition apparatus corresponding to the keyword, and receiving a speech recognition result from the external speech recognition apparatus; and

a speech recognition step of, if said decision step decides that the speech information does not include the keyword, recognizing the speech information.

3. A storage medium that stores a control program for making a computer implement the speech recognition method claimed in claim 2.

4. A control program for making a computer implement the speech recognition method claimed in claim 2.